Multi-perception fusion intelligent robot alignment method and electronic equipment

Abstract

According to the multi-perception fusion intelligent robot alignment method and the electronic equipment, a positioning identifier is deployed on at least one side of a material rack, and the peripheries of material rack feet corresponding to the two sides of the positioning identifier are surrounded by reflective strips respectively, so that the deployment cost is greatly reduced; by measuring the transverse distance between the robot and the two reflective stripes, the robot is accurately controlled to move to the middle position of the two reflective stripes; then, the moving direction of the robot is adjusted according to the relative pose information of the positioning identifier relative to the robot, and it is ensured that the robot travels towards the positioning identifier; finally, the robot is accurately controlled to move to the bottom of the material frame, accurate autonomous navigation and positioning are achieved, the robot can rapidly and accurately complete the jacking task of the material frame, manual intervention is reduced, and the production efficiency is remarkably improved; the method can meet the requirement for variable application sites and has high reusability.

Description

Technical Field

[0001] The present application relates to the technical field of mobile robots, and in particular to a multi-sensory fusion intelligent robot alignment method and electronic equipment. Background Art

[0002] The jack-up AMR, or submersible jack-up AMR (Automated Mobile Robot), is a high-performance mobile robot, mainly composed of a drive device, a body device, a lifting device, etc. It combines technologies such as close-range laser radar and collision sensors, and can dive into the bottom of the rack while running at high speed, lift the rack off the ground using the lifting mechanism, and move it to a designated location to achieve material transportation and transfer.

[0003] Existing submersible lifting AMRs mainly realize precise positioning by identifying the positioning marks (such as QR codes, magnetic strips, etc., each of which contains specific location information, etc.) on the ground through the identification modules (such as cameras, magnetic induction sensors, etc.) carried by them. Through continuous positioning mark recognition, the AMR can move along a predetermined path and realize precise navigation. For details, please refer to the application publication number CN 114326739 A for a high-precision AMR unloading method and AMR vehicle. However, the above scheme has the following disadvantages: first, the deployment cost is high, and a large number of positioning marks need to be laid on the ground, which increases the material cost and labor cost; second, the reusability is poor. When the AMR needs to work in a new environment, the positioning marks need to be re-laid, resulting in a higher migration cost. Summary of the invention

[0004] In view of the above problems, the present application provides a multi-sensory fusion intelligent robot alignment method to solve the problems of high deployment cost and poor reusability caused by laying existing positioning markers on the ground.

[0005] To achieve the above purpose, the inventor provides a multi-sensory fusion intelligent robot alignment method, wherein a positioning mark is deployed on at least one side of the material rack, and the outer periphery of the material rack feet on both sides of the corresponding positioning mark are respectively surrounded by reflective strips; the mobile robot is equipped with a laser radar and an RGB camera;

[0006] The method comprises the following steps:

[0007] Control the mobile robot to move to the front of the rack;

[0008] According to the width of the rack and the position of the positioning mark relative to the mobile robot, the laser radar data is traversed to obtain a high-reflection data point cluster corresponding to the two reflective strips of the rack;

[0009] Calculate the lateral distance between the high-reflection data point clusters of the two reflective strips and the robot;

[0010] According to the lateral distance between the two reflective strips and the robot, the mobile robot is controlled to move a corresponding distance so that the mobile robot reaches the middle of the two reflective strips;

[0011] Adjust the position and posture of the mobile robot so that the moving direction of the mobile robot faces the positioning mark;

[0012] Control the mobile robot to move to the bottom of the rack and lift the rack.

[0013] Furthermore, the step of controlling the mobile robot to move to the front of the rack comprises the following steps:

[0014] The RGB camera identifies the positioning mark within the field of view and obtains the position and posture of the positioning mark relative to the mobile robot;

[0015] Find the positioning mark closest to the mobile robot;

[0016] According to finding the positioning mark, the mobile robot is controlled to move to the front of the material rack corresponding to the positioning mark.

[0017] Furthermore, the step of identifying the positioning mark of the material rack by using an RGB camera to obtain the position and posture of the positioning mark relative to the mobile robot obtains the position and posture of the positioning mark relative to the mobile robot by using an Apriltag algorithm.

[0018] Furthermore, the step of traversing the laser radar data according to the width of the rack and the position of the positioning mark relative to the mobile robot to obtain a high-reflective data point cluster corresponding to the two reflective strips of the rack includes the following steps:

[0019] Obtain lidar data;

[0020] Extract high-reflection data points from the raw LiDAR data;

[0021] Cluster the high-reflection data points to form a data point cluster of reflective strips;

[0022] According to the width of the rack and the position of the positioning mark relative to the mobile robot, the high-reflective data point clusters corresponding to the two reflective strips of the rack are selected from the lidar data.

[0023] Furthermore, the step of controlling the mobile robot to move a corresponding distance according to the lateral distance between the two reflective strips and the robot so that the mobile robot reaches the middle of the two reflective strips comprises the following steps:

[0024] Record the lateral distance between the mobile robot and the left reflective strip as d1, and the lateral distance between the mobile robot and the right reflective strip as d2;

[0025] If d1>d2, the mobile robot moves toward the reflective strip on the left until the difference between the lateral distance d1 between the mobile robot and the reflective strip on the left and the lateral distance d2 between the mobile robot and the reflective strip on the right is within the set threshold;

[0026] If d2>d1, the mobile robot moves toward the reflective strip on the right side until the difference between the lateral distance d1 between the mobile robot and the reflective strip on the left side and the lateral distance d2 between the mobile robot and the reflective strip on the right side is within the set threshold;

[0027] If d1=d2, the mobile robot does not move.

[0028] Furthermore, the step of controlling the mobile robot to move a corresponding distance based on the lateral distance between the two reflective strips and the robot so that the mobile robot reaches the middle of the two reflective strips also includes monitoring the pixel coordinates of the positioning marker in the RGB camera. If it is found that the positioning marker is about to leave the field of view, the angular velocity of rotation is issued in parallel.

[0029] Furthermore, the step of adjusting the posture of the mobile robot so that the moving direction of the mobile robot is toward the positioning mark includes adjusting the posture of the mobile robot according to the posture of the reflective strip relative to the mobile robot so that the moving direction of the mobile robot is toward the positioning mark.

[0030] Furthermore, the step of controlling the mobile robot to move to the bottom of the rack and lifting the rack comprises the following steps:

[0031] Identify the positioning mark of the material rack through an RGB camera to obtain the position and posture of the positioning mark relative to the mobile robot;

[0032] The moving distance of the mobile robot is calculated by combining the position of the positioning mark relative to the mobile robot and the side width of the rack;

[0033] Control the vehicle to move toward the rack according to the moving distance of the mobile robot, and control the mobile robot to move to the bottom of the rack;

[0034] The mobile robot lifts the material rack.

[0035] Furthermore, in the step of controlling the mobile robot to move to the bottom of the material rack and lifting the material rack, after controlling the mobile robot to move to the bottom of the material rack, it also includes adjusting the posture of the mobile robot according to the posture of the reflective strip relative to the mobile robot.

[0036] An electronic device comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of the multi-sensory fusion intelligent robot alignment method are implemented.

[0037] Different from the existing technology, the above technical solution deploys a positioning mark on one side of the material rack and deploys reflective strips on the material rack feet on both sides of the positioning mark, that is, each material rack only needs to correspond to one positioning mark and two reflective strips, which greatly reduces the deployment cost; by measuring the lateral distance from the two reflective strips, the robot is accurately controlled to move to the middle position of the two reflective strips; then, the relative position information of the positioning mark relative to the robot is used to adjust the movement direction of the robot to ensure that the robot moves towards the positioning mark; finally, the robot is accurately controlled to move to the bottom of the material rack to achieve precise autonomous navigation and positioning. The robot can quickly and accurately complete the jacking task of the material rack, reduce manual intervention, and significantly improve production efficiency; this method can meet the changing needs of application sites and has high reusability.

[0038] The above-mentioned records related to the invention content are only an overview of the technical solution of the present application. In order to enable ordinary technicians in the field to more clearly understand the technical solution of the present application, and then implement it according to the text of the specification and the contents recorded in the drawings, and to make the above-mentioned purpose and other purposes, features and advantages of the present application easier to understand, the following is an explanation in combination with the specific implementation mode and drawings of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The drawings are only used to illustrate the principles, implementation methods, applications, characteristics and effects of the specific embodiments of the present invention and other related contents, and shall not be considered as limiting the present application.

[0040] In the drawings of the specification:

[0041] Figure 1 It is a flowchart of the multi-sensory fusion intelligent robot alignment method described in a specific implementation method. DETAILED DESCRIPTION

[0042] In order to explain in detail the possible application scenarios, technical principles, specific schemes that can be implemented, and the purposes and effects that can be achieved, the following is a detailed description of the specific embodiments listed in conjunction with the accompanying drawings. The embodiments described herein are only used to more clearly illustrate the technical solutions of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0043] Reference to "embodiment" herein means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present application. The term "embodiment" appearing in various places in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or association with other embodiments. In principle, in the present application, as long as there is no technical contradiction or conflict, the various technical features mentioned in the embodiments can be combined in any way to form a corresponding implementable technical solution.

[0044] Unless otherwise defined, the technical terms used in this document have the same meanings as those generally understood by those skilled in the art to which this application belongs; the use of relevant terms in this document is only for describing specific embodiments and is not intended to limit this application.

[0045] In the description of this application, the term "and / or" is an expression used to describe the logical relationship between objects, indicating that three relationships may exist, for example, A and / or B, which means: A exists, B exists, and A and B exist at the same time. In addition, the character " / " in this article generally indicates that the objects before and after are in an "or" logical relationship.

[0046] In the present application, terms such as “first” and “second” are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship of quantity, priority or sequence between these entities or operations.

[0047] Without further limitations, in this application, the words "include", "comprises", "has" or other similar open-ended expressions used in sentences are intended to cover non-exclusive inclusion. These expressions do not exclude the presence of additional elements in the process, method or product including the elements, so that the process, method or product including a series of elements may include not only those limited elements, but also other elements not explicitly listed, or also include elements inherent to such process, method or product.

[0048] Similar to the understanding in the Examination Guidelines, in this application, expressions such as "greater than", "less than", "exceed" and the like are understood to exclude the number itself; expressions such as "above", "below", "within" and the like are understood to include the number itself. In addition, in the description of the embodiments of this application, "multiple" means more than two (including two), and similar expressions related to "multiple" are also understood in this way, such as "multiple groups", "multiple times", etc., unless otherwise clearly and specifically limited.

[0049] In the description of the embodiments of the present application, space-related expressions used, such as "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "vertical", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicate the orientation or position relationship based on the orientation or position relationship shown in the specific embodiments or drawings, and are only for the convenience of describing the specific embodiments of the present application or facilitating the reader's understanding, and do not indicate or imply that the referred device or component must have a specific position, a specific orientation, or be constructed or operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present application.

[0050] See also Figure 1 As shown in the figure, a multi-sensory fusion intelligent robot alignment method is used, in which a positioning mark is deployed on one side of the material rack, and reflective strips are deployed on the material rack feet on both sides of the corresponding positioning mark, that is, each material rack only needs to correspond to one positioning mark and two reflective strips, which greatly reduces the deployment cost; by measuring the lateral distance from the two reflective strips, the robot is accurately controlled to move to the middle position of the two reflective strips; then, the relative position information of the positioning mark relative to the robot is used to adjust the movement direction of the robot to ensure that the robot moves towards the positioning mark; finally, the robot is accurately controlled to move to the bottom of the material rack to achieve accurate autonomous navigation and positioning, and the robot can quickly and accurately complete the lifting task of the material rack, reducing manual intervention and significantly improving production efficiency; at the same time, the multi-sensory fusion technology improves the reliability and accuracy of the system, and reduces operational errors caused by inaccurate positioning; the method can meet the changing needs of the application site and has high reusability; the method can flexibly adapt to material racks of different specifications, and there is no requirement for specific specifications of the material racks. It can flexibly adapt to customized material rack requirements, avoiding resource waste caused by inconsistent material rack specifications and improving resource utilization.

[0051] Combination Figure 1 The following is an implementation method of a multi-sensory fusion intelligent robot alignment method of the present application, wherein a positioning mark is deployed on at least one side of the material rack, and the periphery of the material rack feet on both sides of the corresponding positioning mark are respectively surrounded by reflective strips; the mobile robot is equipped with a laser radar and an RGB camera;

[0052] The method comprises the following steps:

[0053] Control the mobile robot to move to the front of the rack;

[0054] According to the width of the rack and the position of the positioning mark relative to the mobile robot, the laser radar data is traversed to obtain a high-reflection data point cluster corresponding to the two reflective strips of the rack;

[0055] Calculate the lateral distance between the high-reflection data point clusters of the two reflective strips and the robot;

[0056] According to the lateral distance between the two reflective strips and the robot, the mobile robot is controlled to move a corresponding distance so that the mobile robot reaches the middle of the two reflective strips;

[0057] Adjust the position and posture of the mobile robot so that the moving direction of the mobile robot faces the positioning mark;

[0058] Control the mobile robot to move to the bottom of the rack and lift the rack.

[0059] The above positioning mark includes specific location information and unique ID data to achieve accurate positioning; of course, it can also include task information, material information on the material rack, etc. The above positioning mark can be a QR code, a barcode, an RFID tag, etc. Preferably, it is a QR code, which has the advantages of large amount of information, fast recognition speed, high accuracy, etc., and is suitable for AMR positioning identification.

[0060] The rack in the step of controlling the mobile robot to move to the front of the rack can be a designated rack that the mobile robot moves to according to instructions, or can be the nearest rack that the mobile robot finds; the nearest rack that the mobile robot finds and moves to the front of the rack specifically includes the following steps:

[0061] The RGB camera identifies the positioning mark within the field of view and obtains the position and posture of the positioning mark relative to the mobile robot;

[0062] Find the positioning mark closest to the mobile robot;

[0063] According to finding the positioning mark, the mobile robot is controlled to move to the front of the material rack corresponding to the positioning mark.

[0064] The above RGB camera identifies the positioning mark within the field of view, and the position of the positioning mark relative to the mobile robot can be obtained by using the Apriltag algorithm to identify the positioning mark within the field of view. Specifically, the following steps are included:

[0065] Get images from RGB camera;

[0066] Decoding: Use edge detection algorithms (such as Canny edge detection) to find the four vertices of the positioning mark from the image; use the four vertices to perform perspective transformation and restore the detected quadrilateral to a standard square (since the positioning mark may be tilted at an angle in three-dimensional space, the image can be corrected through perspective transformation); identify the image after perspective transformation to obtain the content of the positioning mark.

[0067] Pose estimation: Obtain the coordinates of the pixel points of the positioning marker in the image; use a pose estimation algorithm (such as the PnP algorithm) to calculate the pose of the positioning marker relative to the mobile robot based on the coordinates of the pixel points of the positioning marker in the image, the intrinsic and extrinsic parameters of the RGB camera, and the actual size of the label.

[0068] Each positioning mark represents a material rack. The position of the positioning mark relative to the mobile robot is the position of the material rack relative to the mobile robot. Finding the nearest positioning mark is finding the nearest material rack, and then controlling the mobile robot to move to the front of the material rack.

[0069] The above step of traversing the laser radar data according to the width of the rack and the position of the positioning mark relative to the mobile robot to obtain a high-reflective data point cluster corresponding to the two reflective strips of the rack includes the following steps:

[0070] Obtain lidar data;

[0071] Extract high-reflection data points from the raw LiDAR data;

[0072] Cluster the high-reflection data points to form a data point cluster of reflective strips;

[0073] According to the width of the rack and the position of the positioning mark relative to the mobile robot, the high-reflective data point clusters corresponding to the two reflective strips of the rack are selected from the lidar data.

[0074] The above step of calculating the lateral distance between the high-reflective data point clusters of the two reflective strips and the robot may include the following steps:

[0075] If the coordinates of the reflective strip on the left are (x1, y1), the coordinates of the reflective strip on the right are (x2, y2);

[0076] Then the lateral distance between the mobile robot and the reflective strip on the left is d1=x-x1;

[0077] The lateral distance between the mobile robot and the right reflective strip is d2=x-x2.

[0078] There are various methods for controlling the mobile robot to move a corresponding distance according to the lateral distance between the two reflective strips and the robot so that the mobile robot reaches the middle of the two reflective strips.

[0079] In some embodiments, the average lateral distance between the two reflective strips can be calculated as d mid =(d1+d2) / 2;

[0080] The distance d that the mobile robot needs to move is move =d mid -d1;

[0081] If d move is positive, the robot needs to move left by d move ; if d move If it is negative, the robot needs to move right by d move .

[0082] In some embodiments, a threshold value may be set, which is the difference between the lateral distance d1 between the mobile robot and the reflective strip on the left and the lateral distance d2 between the mobile robot and the reflective strip on the right; specifically, the following steps are included:

[0083] If d1>d2, the mobile robot moves toward the reflective strip on the left until the difference between the lateral distance d1 between the mobile robot and the reflective strip on the left and the lateral distance d2 between the mobile robot and the reflective strip on the right is within the set threshold;

[0084] If d2>d1, the mobile robot moves toward the reflective strip on the right side until the difference between the lateral distance d1 between the mobile robot and the reflective strip on the left side and the lateral distance d2 between the mobile robot and the reflective strip on the right side is within the set threshold;

[0085] If d1=d2, the mobile robot does not move.

[0086] Of course, in the above steps, the pixel coordinates of the positioning mark in the RGB camera can also be monitored. If the positioning mark is about to leave the field of view, the angular velocity of rotation is sent in parallel. By real-time monitoring of the pixel coordinates of the positioning mark in the camera, the mobile robot can more accurately determine the relative position relationship between itself and the positioning mark, thereby adjusting the movement strategy to ensure that the mobile robot can stably and accurately move to the middle of the two reflective strips.

[0087] It should be noted that the above-mentioned mobile robot moves toward the reflective strip on the left or the reflective strip on the right, which means that the mobile robot can rotate to the left for a certain angle and then move to move toward the reflective strip on the left; similarly, the mobile robot can also rotate to the right for a certain angle and then move to move toward the reflective strip on the left. The specific mobile robot can also choose to move to the left rear, move to the left front, or rotate to the left first and then go straight, so that the mobile robot moves to the reflective strip on the left; similarly, the mobile robot can also choose to move to the right rear, move to the right front, or rotate to the right first and then go straight, so that the mobile robot moves to the reflective strip on the right.

[0088] The above-mentioned step of adjusting the posture of the mobile robot so that the moving direction of the mobile robot is toward the positioning mark can be performed by adjusting the posture of the mobile robot according to the posture of the positioning mark relative to the mobile robot so that the moving direction of the mobile robot is toward the positioning mark. The posture of the mobile robot can also be adjusted according to the posture of the reflective strip relative to the mobile robot so that the moving direction of the mobile robot is toward the positioning mark. Specifically, it can be determined whether the pixel coordinates of the center point of the RGB camera are in the middle of the two reflective strips; if so, the moving direction of the mobile robot is toward the positioning mark; otherwise, the mobile robot is controlled to rotate in place and the above steps are repeated.

[0089] The above step of controlling the mobile robot to move to the bottom of the rack and lifting the rack includes the following steps:

[0090] Identify the positioning mark of the material rack through an RGB camera to obtain the position and posture of the positioning mark relative to the mobile robot;

[0091] The moving distance of the mobile robot is calculated by combining the position of the positioning mark relative to the mobile robot and the side width of the rack;

[0092] Control the vehicle to move toward the rack according to the moving distance of the mobile robot, and control the mobile robot to move to the bottom of the rack;

[0093] The mobile robot lifts the material rack.

[0094] The RGB camera identifies the positioning mark of the rack, and the position of the positioning mark relative to the mobile robot can also be obtained by using the Apriltag algorithm. The distance of the positioning mark relative to the mobile robot can be known by the position of the positioning mark relative to the mobile robot; the side width of the rack refers to the width of the rack in the forward direction of the mobile robot, which is usually known and can be obtained by pre-measurement. Therefore, the moving distance of the mobile robot can be calculated by combining the distance of the positioning mark relative to the mobile robot and the side width of the rack.

[0095] Specifically, the moving distance of the mobile robot may be half of the side width of the charging rack from the positioning mark relative to the mobile robot to ensure that the center of the vehicle is aligned with the center of the charging rack.

[0096] Of course, after controlling the mobile robot to move to the bottom of the rack, the position of the mobile robot can also be adjusted according to the position of the reflective strips relative to the mobile robot. Keeping the mobile robot in the middle of the two reflective strips can further improve the positioning accuracy of the robot at the bottom of the rack, avoid the robot shaking or shifting during operation when the relative position of the robot and the rack is incorrect, thereby affecting the safety, efficiency and accuracy of the operation, and ensure that the robot remains stable during the operation, improving the stability of the operation.

[0097] The present invention also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the steps of the multi-sensory fusion intelligent robot alignment method are implemented.

[0098] The processor described in the embodiments of the present application can be implemented by hardware, firmware, software or a combination thereof, and can use a circuit, a single or multiple application-specific integrated circuits (Application Specific Integrated Circuit, ASIC), a digital signal processor (Digital Signal Processor, DSP), a digital signal processing device (Digital Signal Processing Device, DSPD), a programmable logic device (Programmable Logic Device, PLD), a field programmable gate array (Field Programmable Gate Array, FPGA), a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, at least one of a microprocessor, and also includes other physical, biological or chemical structures that can achieve similar or equivalent functions to the processors listed above, such as biological neurons, quantum computing units, DNA computing units, etc., so that the processor can execute some or all of the steps in the computer program or method involved in the various embodiments of the present application, or any combination of the steps mentioned therein.

[0099] The computer program involved in the embodiment can be stored in a computer device readable storage medium, which includes but is not limited to a disk, a tape, a magnetic card, a floppy disk, a flash memory, an optical disk, an optical card, a read-only memory (ROM), a random access memory (RAM), an erasable programmable ROM (EPROM) and an electrically erasable programmable ROM (EEPROM), etc., and also includes other biological, physical or chemical structures that can achieve the same or equivalent functions as the storage media listed above, such as DNA, RNA, protein and other units with information storage capabilities. In a specific embodiment, the storage medium involved can be one of the above-mentioned media types, or a combination of the above-mentioned media types. In different embodiments, the computer program involved in the embodiment can be stored in a single medium in a centralized manner, or it can be stored in multiple media in a distributed manner. The memory containing the computer device readable storage medium can be a non-volatile memory or a random access memory. These computer device readable storage media can be built into the device, or they can be connected to the device involved in the embodiment as an external device or a part of an external device. In some embodiments, a memory with a computer device readable storage medium is deployed locally; in other embodiments, a solution of deploying the memory away from the processor may also be adopted, such as a network attached memory accessed via an RF circuit or an external port and a communication network, wherein the communication network may be the Internet, one or more intranets, a local area network (LAN), a wide area network (WLAN), a storage area network (SAN), etc., or a suitable combination thereof, as long as the computer device can access the memory. In addition, the computer program involved in the embodiment may be stored in plaintext / ciphertext form, or may be designed as training data, which may be integrated and reorganized through model training and implicitly stored in the parameter state of a deep neural network or other machine learning model.

[0100] Finally, it should be noted that although the above embodiments have been described in the specification and drawings of this application, this does not limit the scope of patent protection of this application. All technical solutions generated by replacing or modifying equivalent structures or equivalent processes based on the essential concept of this application using the contents recorded in the specification and drawings of this application, as well as directly or indirectly implementing the technical solutions of the above embodiments in other related technical fields, are included in the scope of patent protection of this application.

Claims

1. A multi-sensory fusion intelligent robot alignment method, characterized in that: At least one side of the rack is equipped with a positioning mark, and the outer periphery of the rack feet on both sides of the corresponding positioning mark are surrounded by reflective strips; the mobile robot is equipped with a laser radar and an RGB camera; The method comprises the following steps: Control the mobile robot to move to the front of the rack; According to the width of the rack and the position of the positioning mark relative to the mobile robot, the laser radar data is traversed to obtain a high-reflection data point cluster corresponding to the two reflective strips of the rack; Calculate the lateral distance between the high-reflection data point clusters of the two reflective strips and the robot; According to the lateral distance between the two reflective strips and the robot, the mobile robot is controlled to move a corresponding distance so that the mobile robot reaches the middle of the two reflective strips; Adjust the position and posture of the mobile robot so that the moving direction of the mobile robot faces the positioning mark; Control the mobile robot to move to the bottom of the rack and lift the rack.

2. The multi-sensory fusion intelligent robot alignment method according to claim 1 is characterized in that: The step of controlling the mobile robot to move to the front of the rack comprises the following steps: The RGB camera identifies the positioning mark within the field of view and obtains the position and posture of the positioning mark relative to the mobile robot; Find the positioning mark closest to the mobile robot; According to finding the positioning mark, the mobile robot is controlled to move to the front of the material rack corresponding to the positioning mark.

3. The multi-sensory fusion intelligent robot alignment method according to claim 2 is characterized in that: The step of identifying the positioning mark of the material rack by using an RGB camera to obtain the position and posture of the positioning mark relative to the mobile robot is to obtain the position and posture of the positioning mark relative to the mobile robot by using the Apriltag algorithm.

4. The multi-sensory fusion intelligent robot alignment method according to claim 1 is characterized in that: The step of traversing the laser radar data according to the width of the rack and the position of the positioning mark relative to the mobile robot to obtain a high-reflective data point cluster corresponding to the two reflective strips of the rack includes the following steps: Obtain lidar data; Extract high-reflection data points from the raw LiDAR data; Cluster the high-reflection data points to form a data point cluster of reflective strips; According to the width of the rack and the position of the positioning mark relative to the mobile robot, the high-reflective data point clusters corresponding to the two reflective strips of the rack are selected from the lidar data.

5. The multi-sensory fusion intelligent robot alignment method according to claim 1, characterized in that: The step of controlling the mobile robot to move a corresponding distance according to the lateral distance between the two reflective strips and the robot so that the mobile robot reaches the middle of the two reflective strips comprises the following steps: Record the lateral distance between the mobile robot and the left reflective strip as d1, and the lateral distance between the mobile robot and the right reflective strip as d2; If d1>d2, the mobile robot moves toward the reflective strip on the left until the difference between the lateral distance d1 between the mobile robot and the reflective strip on the left and the lateral distance d2 between the mobile robot and the reflective strip on the right is within the set threshold; If d2>d1, the mobile robot moves toward the reflective strip on the right side until the difference between the lateral distance d1 between the mobile robot and the reflective strip on the left side and the lateral distance d2 between the mobile robot and the reflective strip on the right side is within the set threshold; If d1=d2, the mobile robot does not move.

6. The multi-sensory fusion intelligent robot alignment method according to claim 1, characterized in that: The step of controlling the mobile robot to move a corresponding distance according to the lateral distance between the two reflective strips and the robot so that the mobile robot reaches the middle of the two reflective strips also includes monitoring the pixel coordinates of the positioning mark in the RGB camera. If it is found that the positioning mark is about to leave the field of view, the angular velocity of rotation is issued in parallel.

7. The multi-sensory fusion intelligent robot alignment method according to claim 1, characterized in that: The step of adjusting the posture of the mobile robot so that the moving direction of the mobile robot is toward the positioning mark includes adjusting the posture of the mobile robot according to the posture of the reflective strip relative to the mobile robot so that the moving direction of the mobile robot is toward the positioning mark.

8. The multi-sensory fusion intelligent robot alignment method according to claim 1, characterized in that: The step of controlling the mobile robot to move to the bottom of the rack and lifting the rack comprises the following steps: Identify the positioning mark of the material rack through an RGB camera to obtain the position and posture of the positioning mark relative to the mobile robot; The moving distance of the mobile robot is calculated by combining the position of the positioning mark relative to the mobile robot and the side width of the rack; Control the vehicle to move toward the rack according to the moving distance of the mobile robot, and control the mobile robot to move to the bottom of the rack; The mobile robot lifts the material rack.

9. The multi-sensory fusion intelligent robot alignment method according to claim 1, characterized in that: In the step of controlling the mobile robot to move to the bottom of the material rack and lifting the material rack, after controlling the mobile robot to move to the bottom of the material rack, the step also includes adjusting the posture of the mobile robot according to the posture of the reflective strip relative to the mobile robot.

10. An electronic device, characterized in that: It includes a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the multi-sensory fusion intelligent robot alignment method as described in any one of claims 1 to 9 are implemented.

Images